Data Scientist

Samsung Electronics•Taylor, TX

14d•$76,000 - $145,000•Onsite

About The Position

As a Data Scientist at Samsung Austin Semiconductor, you will play a critical role in optimizing and improving semiconductor manufacturing processes. You will focus on developing advanced abnormality detection systems to monitor complex data streams and building sophisticated root cause analysis applications to drive quality improvement. By designing and implementing scalable machine learning pipelines, you will help reduce manufacturing variability and accelerate the identification of process issues, directly impacting the efficiency and quality of our semiconductor fabrication. This role requires a strong foundation in analytical problem-solving, statistics, and the machine learning expertise necessary to deploy predictive models at an industrial scale. We are looking for an adaptable problem-solver who thrives in an environment of autonomy and collaboration. While prior experience in the semiconductor industry is a plus, it is not required for success; instead, you will learn through hands-on projects and working with our experienced team members. Our team emphasizes a lean, Agile mindset, focusing on rapid development and iterating based on feedback to drive continuous improvement. As a critical thinker, you will have the autonomy to identify high-value problems and design and implement the best technical solutions.

Requirements

Bachelor's or higher in Computer Science, Data Science, or a related quantitative field (or equivalent professional experience).
3+ years of professional experience applying machine learning in an industrial setting (5+ years for those without a graduate degree).
Strong background in statistics.
Expert-level proficiency in PySpark for large-scale data processing.
Proven experience implementing abnormality or anomaly detection algorithms, particularly with time-series data.
Demonstrated experience working in an Agile development framework.

Nice To Haves

Prior experience in the semiconductor industry is a plus.

Responsibilities

Develop and optimize abnormality detection algorithms of time-series data to monitor diverse semiconductor data sources.
Model control theory applications to optimize process stability, with a focus on incorporating advanced analytics & ML.
Manage all stages of the ML development pipeline, from data ingestion and feature engineering to model deployment.
Design and implement the technical architecture required to support scalable ML development and execution.
Communicate complex technical findings effectively to both fellow data scientists and cross-functional stakeholders.
Collaborate within an Agile framework to translate manufacturing challenges into technical ML solutions.
Develop and maintain internal applications used for root cause analysis to drive yield improvement.
Analyze large and complex datasets to identify trends and patterns that drive measurable system improvements.
Enhance data collection and processing workflows to create robust, high-quality test datasets that ensure model accuracy, relevance, and integrity.